To investigate the correlation of total imaging burden score and inflammatory and metabolic indexes with cognitive impairment in cerebral small vessel disease (CSVD), and establish an early prediction model. Methods: A retrospective study was performed on 170 CSVD patients who visited the Department of Neurology, Fifth Clinical School of Medicine, Shanxi Medical University from September 2020 to May 2022. According to their Montreal Cognitive Assessment (MoCA) scale scores, the patients were divided into the no cognitive impairment group (n= 0) and cognitive impairment group (n=110). Then, 140 patients were randomly selected as the training set and 30 as the validation set. General data, CSVD total burden score, inflammatory indicators [lipoprotein phospholipase A2 (Lp-PLA2), interleukin 6 (IL-6)] and metabolic indicators [homocysteine (Hcy) and cystatin C (CysC)] of the two groups in the training set were compared. Logistic multivariate regression analysis was performed on the difference factors, independent risk factors were selected, nomograms were constructed, predictive model were established, and model performance was evaluated. Results: The CSVD total burden score and the expression levels of serum Lp-PLA2, IL-6, Hcy, and CysC in the cognitive impairment group were higher than those in the non-cognitive impairment group, and the differences were statistically significant (P<0.05). Multivariate Logistic regression analysis showed that the increasing of CSVD total burden score and serum Lp-PLA2 and Hcy levels were independent risk factors for cognitive impairment in patients with CSVD. These three items were used to draw the ROC curve for the diagnosis of secondary cognitive impairment in CSVD patients, and the area under the curve was 0.775, 0.795, 0.877, and 0.929. By constructing the nomogram of the CSVD total burden score and serum Lp-PLA2 and Hcy, the prediction was drawn. The ROC curves of the model and the CSVD total burden score alone to diagnose secondary cognitive impairment of CSVD patients in the validation set were evaluated, and the area under the ROC curve of the model and the CSVD total burden score alone was 0.935 and 0.905, respectively. Conclusion: The combined imaging total burden score and blood inflammatory and metabolic indicators are superior to imaging assessment alone in predicting the risk of cognitive impairment in CSVD, and they provide certain clues for the early diagnosis of cognitive impairment in patients with CSVD.